PorTAL ports LoRA task adapters across LLMs, slashing retraining costs
PorTAL learns a model-agnostic task latent plus a thin per-model hypernetwork that generates LoRA weights. After training on one base, it can be refit to new LLMs, recovering ~98% of a full LoRA’s accuracy on Qwen3-8B and ~94% on Gemma-3 while using half the calibration data. This cuts the cost of repeatedly fine-tuning each new model.